Joyce Gill

Adversarial Review: three agents hit 75.2% on SWE-bench Verified by forcing disagreement

Cornell and Stanford researchers' three-agent code-review protocol, Adversarial Review, hits 75.2% pass@1 on SWE-bench Verified versus 71.6% for zero-shot Claude Code and 72.6% for a five-agent MARS system, at 4.5x the tokens.